TY - JOUR
T1 - Novel Artificial intelligence systems in detecting adenomas in colonoscopy
T2 - a systemic review and network meta-analysis.
AU - Kumar, Sunny
AU - Maheshwari, Mahveer
AU - Aleem, Shahnoor
AU - Batool, Zoha
AU - Lal, Amar
AU - Syed, Saifullah
AU - Daterdiwala, Nida Fatima
AU - Memon, Hina Fatima
AU - Azeem, Jaweria
AU - Qamari, Sajida Moiz Hussain
AU - Jawwad, Mohammad
N1 - Publisher Copyright:
© 2025 Lippincott Williams and Wilkins. All rights reserved.
PY - 2025
Y1 - 2025
N2 - Background: Artificial intelligence (AI) has the potential to improve adenoma detection rates (ADRs) during colonoscopy, but the efficacy of various AI-assisted systems remains unclear. Objective: To evaluate and compare the effectiveness of different AI-assisted systems for detecting colorectal neoplasia during colonoscopy. Design: A systematic literature search of PubMed, Scopus, and Google Scholar databases was conducted up to March 4, 2025, to identify randomized controlled trials (RCTs) comparing AI-assisted colonoscopy to conventional colonoscopy. The analysis included AI systems such as GIGenius (Medtronic), CAD-EYE (Fujifilm), Endoangel, Endoscreener, and EndoAID. The primary outcome was adenoma detection rate (ADR), analyzed using random effects models to calculate pooled odds ratios (OR) and 95% confidence intervals (CI). SUCRA rankings and subgroup analyses were also performed. Results: Seventeen RCTs with 10,547 participants were included. EndoAngel showed the highest efficacy (OR 1.84, 95% CI 1.50–2.30; SUCRA 0.9), followed by EndoAID (OR 1.64, 95% CI 1.20–2.26; SUCRA 0.7). CAD-EYE and GI-Genius were similarly ranked (OR 1.46 and 1.45, respectively). Endoscreener was ranked just above the control group (OR 1.37, 95% CI 1.20–1.56; SUCRA 0.4). Conclusion: AI-assisted colonoscopy systems showed improved ADR detection rates compared with traditional colonoscopy.
AB - Background: Artificial intelligence (AI) has the potential to improve adenoma detection rates (ADRs) during colonoscopy, but the efficacy of various AI-assisted systems remains unclear. Objective: To evaluate and compare the effectiveness of different AI-assisted systems for detecting colorectal neoplasia during colonoscopy. Design: A systematic literature search of PubMed, Scopus, and Google Scholar databases was conducted up to March 4, 2025, to identify randomized controlled trials (RCTs) comparing AI-assisted colonoscopy to conventional colonoscopy. The analysis included AI systems such as GIGenius (Medtronic), CAD-EYE (Fujifilm), Endoangel, Endoscreener, and EndoAID. The primary outcome was adenoma detection rate (ADR), analyzed using random effects models to calculate pooled odds ratios (OR) and 95% confidence intervals (CI). SUCRA rankings and subgroup analyses were also performed. Results: Seventeen RCTs with 10,547 participants were included. EndoAngel showed the highest efficacy (OR 1.84, 95% CI 1.50–2.30; SUCRA 0.9), followed by EndoAID (OR 1.64, 95% CI 1.20–2.26; SUCRA 0.7). CAD-EYE and GI-Genius were similarly ranked (OR 1.46 and 1.45, respectively). Endoscreener was ranked just above the control group (OR 1.37, 95% CI 1.20–1.56; SUCRA 0.4). Conclusion: AI-assisted colonoscopy systems showed improved ADR detection rates compared with traditional colonoscopy.
KW - Artificial intelligence
KW - adenoma detection rate
KW - colonoscopy
KW - colorectal neoplasia
UR - https://www.scopus.com/pages/publications/105013896852
U2 - 10.14309/ctg.0000000000000904
DO - 10.14309/ctg.0000000000000904
M3 - Article
AN - SCOPUS:105013896852
SN - 2155-384X
JO - Clinical and Translational Gastroenterology
JF - Clinical and Translational Gastroenterology
M1 - 10.14309/ctg.0000000000000904
ER -